Language Modeling

FIRMA: Bidirectional Formal-Informal Mathematical Language Alignment with Proof-Theoretic Grounding EMNLP 2025 First-Step Advantage: Importance of Starting Right in Multi-Step Math Reasoning ACL 2025 Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs EMNLP 2025 Flexible and Efficient Grammar-Constrained Decoding ICML 2025 FOCUS: A Benchmark for Targeted Socratic Question Generation via Source-Span Grounding IJCNLP 2025 Forest for the Trees: Overarching Prompting Evokes High-Level Reasoning in Large Language Models NAACL 2025 FrameEOL: Semantic Frame Induction using Causal Language Models EMNLP 2025 From Anger to Joy: How Nationality Personas Shape Emotion Attribution in Large Language Models IJCNLP 2025 From Human Reading to NLM Understanding: Evaluating the Role of Eye-Tracking Data in Encoder-Based Models ACL 2025 From Language Models over Tokens to Language Models over Characters ICML 2025 From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment ACL 2025 Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning ACL 2025 FUSE: Universal Speech Enhancement using Multi‐Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Interspeech 2025 Gathering Compositionality Ratings of Ambiguous Noun-Adjective Multiword Expressions in Galician NAACL 2025 GBEM-UA: Gender Bias Evaluation and Mitigation for Ukrainian Large Language Models ACL 2025 GCG-Based Artificial Languages for Evaluating Inductive Biases of Neural Language Models CoNLL 2025 Generalized Interpolating Discrete Diffusion ICML 2025 Generation of Russian Poetry of Different Genres and Styles Using Neural Networks with Character-Level Tokenization NAACL 2025 Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction ICML 2025 Generative Monoculture in Large Language Models ICLR 2025 Generative Verifiers: Reward Modeling as Next-Token Prediction ICLR 2025 GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning EMNLP 2025 Geometry Informed Tokenization of Molecules for Language Model Generation ICML 2025 GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts Architecture ACL 2025 Global Eye: Breaking the “Fixed Thinking Pattern” during the Instruction Expansion Process ACL 2025